INDEX

Explanations

references to personal experiences and self-identity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itself

-0.25

ness

-0.21

 themselves

-0.20

ly

-0.19

wers

-0.18

ting

-0.17

rette

-0.16

appen

-0.16

ship

-0.16

nya

-0.16

POSITIVE LOGITS

/us

0.63

/her

0.43

 personally

0.33

/my

0.30

zelf

0.28

-mÃªme

0.28

adows

0.27

adow

0.27

SELF

0.27

andering

0.26

Activations Density 0.248%

references to personal experiences and self-identity

No Comments

No Known Activations